In Episode 40, Pierson and Bilal get into something most people are completely overlooking.

Using Obsidian and local Markdown files to build a personal knowledge base that an LLM organizes, interlinks, and updates for you every single day. Your notes, your transcripts, your ideas — structured like your own Wikipedia, maintained by AI.

From there they cover:

• Why local-first AI models are winning the privacy argument
• How open source is quietly taking over
• What Opus 4.7 actually changes for developers
• Pierson's live demo of Claw Connect — a peer-to-peer protocol that lets AI agents talk directly to each other, across any model or harness
  

Two Claude Code instances. On screen. Having their own conversation. It gets wild.

Lots of rabbit holes. All worth it.

🔗 Links mentioned:

• Opus 4.7: https://www.anthropic.com/news/claude-opus-4-7
• Claude Code Routines: https://code.claude.com/docs/en/routines
• Gemini TTS: https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview
• Andrej Karpathy on LLM Knowledge Bases: https://x.com/karpathy/status/2039805659525644595
  
  Chapters:
  
  00:00 Episode 40 & Building a Personal Knowledge Base with Obsidian
  08:10 Daily AI Routines, Claude Code & Automating Your Workflow
  13:46 Local AI Models, Open Source & the Privacy Argument
  24:29 Opus 4.7, Energy, Intelligence & What's Next
  39:37 Introducing Claw Connect: Peer-to-Peer Agent Communication
  56:18 Two AI Agents Talking Live & the Future of Agent Collaboration
  

🐦 Follow the hosts:

• Pierson → https://x.com/piersonmarks
• Bilal → https://x.com/deepwhitman
  

📺 More episodes: https://www.youtube.com/@JellypodAi

In Episode 39, Pierson and Bilal cover a lot of ground, starting with a chance meeting at a rooftop event in SF that led to a conversation about AI agents hosting their own podcasts.

They break down Clawcast (what happens when your AI agent can invite other agents to record a podcast), why agent-to-agent communication might be the next big wave, and how smart contracts could use AI to handle deals and settle disputes automatically.

Then they get into the AI model race, Anthropic vs OpenAI, what 10 trillion parameter models actually mean, why old GPUs aren't obsolete yet, and how robotics is quietly reshaping Amazon's warehouses.

Lots of rabbit holes. All worth it.

🔗 Links mentioned:

• Neural Noise: https://github.com/leopiney/neuralnoise
• Anthropic Mythos / Project Glasswing: https://www.anthropic.com/glasswing
• Dylan Patel & Dwarkesh Patel Podcast: https://www.youtube.com/watch?v=mDG_Hx3BSUE
  
  

🐦 Follow the hosts:

• Pierson → https://x.com/piersonmarks
• Bilal → https://x.com/deepwhitman
  

📺 More episodes: https://www.youtube.com/@JellypodAi

Chapters:

00:00 Introduction & What's Been Going On This Week

02:32 Neural Noise & Clawcast: AI Agents Hosting Podcasts

11:09 Agent Communication, Smart Contracts & Killing the Middleman

21:40 Game Theory, Geopolitics & the AI Model Race

30:30 Chips, Hardware & Why Old GPUs Still Matter

36:17 Robotics, Dark Factories & Amazon's Future

On Episode 38, we sit down with Koyal AI (YC F25) founder & CEO Mehul Agarwal (https://x.com/meh_agarwal) to discuss the future of filmmaking with AI.

His goal? Replacing the camera, not the filmmaker.

Mehul shares the journey of Koyal's development, from inception as a research paper at NeurIPS 2024 to its most recent v2.5 launch. Covering a range of topics from AI video, world models, benchmarking, user interfaces, and more.

Chapters

• 00:00 Introducing Koyal: The AI Filmmaking Platform
• 06:04 Combining Creativity and Technology
• 11:26 Koyal's State-of-the-Art Consistency
• 22:25 Creating Realistic Avatars
• 27:29 User Interface for Video Editing
• 36:23 Impact of Memetic Content
• 41:26 Predictions for Video and Image Technology

Show Notes:

• NeurIPS 2024 Paper - CHARCHA: https://www.ri.cmu.edu/cmu-alumni-launch-koyal-for-safe-ai-video-creation/
• Koyal AI: https://koyal.ai/

On Episode 37, hosts Pierson (https://x.com/piersonmarks) and Bilal (https://x.com/deepwhitman) discuss OpenAI shutting down Sora refocusing on coding and ChatGPT, the automated improvement cycles in AI models, and the concept of an agent-first approach in software development (an intro to the /superpowers plugin).

Show Notes:

• Sora Shutting Down: https://openai.com/sora/
• Superpowers Plugin: https://github.com/obra/superpowers
• Stripe Projects: https://projects.dev/
• Fuma Docs: https://www.fumadocs.dev/

Chapters:

• 00:00 Introduction and Podcast Overview
• 09:05 Agent-First Approach in Software Development
• 27:45 Superpowers Plugin for Cloud Development
• 33:00 Quality of Life Enhancements in Cloud Development
• 39:14 Discussion on API Documentation and OpenAPI Spec

On Episode 36, hosts Pierson (https://x.com/piersonmarks) and Bilal (https://x.com/deepwhitman) give a first look into Google Stitch 2 (and a few other Google Labs products). Coming off a fun after-party hosted by our friends @FAL, they also dig into Bilal's open-sourced LoFi Music dataset of 160 free-to-use songs, Raycast's Glaze mac-app builder, and more.

Show Notes:

• Google Stitch 2: https://stitch.withgoogle.com/
• Raycast Glaze: https://www.glaze.app/
• Open LoFi: https://github.com/btahir/open-lofi
• FAL: https://fal.ai/

Chapters

• 00:00 Exploring the Generative Media Community
• 07:15 Google Labs and Experimental AI Projects
• 15:04 Personalized Software and Vibe Coding
• 22:24 AI-Generated Art and Design
• 29:32 Design System and Theme Generation
• 35:38 AI-Generated Lo-Fi Music

On Episode 35, hosts Pierson (https://x.com/piersonmarks) and Bilal (https://x.com/deepwhitman) cover the latest in Generative Media, with Netflix acquiring Ben Afleck's AI startup InterPositive for $600M, Replit Agent 4 (with a $9B new funding round), and Polsia running your business while you sleep. Also, a Punch the Monkey AI short.

Show Notes:

• Ben Afleck's AI Startup InterPositive: https://techcrunch.com/2026/03/11/netflix-may-have-paid-600-million-for-ben-afflecks-ai-startup/
• Replit Agent 4 and their latest funding round @ $9B https://replit.com/news/funding-announcement
• Punch the Monkey AI Film: https://x.com/venturetwins/status/2029961922783895958?s=20
• Wonder Studios: https://wonderstudios.com/
  

On Episode 34, hosts Pierson (@piersonmarks) and Bilal (@deepwhitman) cover Google NotebookLM's new cinematic video overviews, GPT 5.4, Claude Code Skills benchmarks, and Cursor's new automations.

Show Notes:

• NotebookLM Cinematic Video Overviews: https://blog.google/innovation-and-ai/products/notebooklm/generate-your-own-cinematic-video-overviews-in-notebooklm/
• GPT 5.4 https://openai.com/index/introducing-gpt-5-4/
• Cursor Automations: https://cursor.com/blog/automations
• React Grab: https://www.react-grab.com/
• Claude Code Skills 2.0: https://code.claude.com/docs/en/skills
• Google Workspace CLI: https://www.npmjs.com/package/@googleworkspace/cli

Chapters

• 00:00 Generative Media and AI
• 08:51 Evolution of AI Models and Releases
• 22:09 Automation and Task Assignment in AI
• 29:17 Cloud Code Skill Creator
• 36:18 Design and Code Integration
• 43:55 Verifiability in Design and Creative Fields

On Episode 33 of Creative Flux, hosts Pierson (@piersonmarks) and Bilal (@deepwhitman) cover

Claude Code's new /remote-control feature, the dead internet theory, how to control camera angles in image gen models, PrunaAI for cheap image and video generation, real-time weather visualization with Nano Banana 2, and Quiver AI for SVG generation and animation.

Show Notes:

• Nano Banana 2: https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/
• Quiver AI (SVG): https://quiver.ai/
• PrunaAI (pVideo & pImage): https://replicate.com/prunaai/p-video
• Camera Angle UI: https://x.com/Framer_X/status/2025912264256307447?s=20
• Camera Angle Qwen Image Edit Model: https://fal.ai/models/fal-ai/qwen-image-edit-2511-multiple-angles

Chapters

• 00:00 Claude Code Remote Control
• 05:02 AI-Generated Content
• 10:05 The Future of Media and Content Creation
• 29:32 Creative Control with Open Source Models
• 35:32 Pruna AI and Low-Cost Video Generation
• 42:00 Quiver AI and SVG Generation